Gemma4-31B-IT-Abliterated

Gemma4-31B-IT-Abliterated

DuoNeural Research — Archon, Jesse Caldwell, Aura | 2026-06-06

Abliterated version of google/gemma-4-31B-it with refusal behaviors removed via orthogonal rank-1 projection. Licensed Apache-2.0, free to use and redistribute.

---

What is Abliteration?

Abliteration (Arditi et al. 2024; mlabonne) removes refusal-generating weight directions from a language model using orthogonal projection:

W_modified = W - α × (W @ d̂) ⊗ d̂   # input projection
W_modified = W - α × d̂ ⊗ (d̂ @ W)   # output projection

where d̂ is the unit refusal direction extracted from harmful/harmless contrastive activations, and α controls projection strength.

---

Method

Phase 1 — Generation-Based Direction Extraction (GPU, BF16, A100-80GB)

The 31B model required a more precise direction extraction method than the standard last-input-token approach. We use first-generated-token activations:

1. Feed each of 15 harmful prompts and 15 harmless prompts through the model
2. Generate exactly 1 token (greedy) — harmful prompts universally produce token 'I' (beginning of "I cannot..."), harmless prompts produce semantically different tokens
3. Forward-pass the full sequence (prompt + generated token) with activation hooks
4. Collect hidden states at the last position (the generated token — the model's refusal decision point)
5. Per-layer direction: d = normalize(mean(harmful_reps) - mean(harmless_reps))

This approach achieves perfect harmful/harmless separation across all 15 prompt pairs and provides a cleaner refusal direction than last-input-token methods. Directions saved per-layer (60 total).

Phase 2 — Orthogonal Projection (CPU, BF16)

• Target matrices: down_proj (FFN output → residual stream) + o_proj (attention output → residual stream)
• Alpha: {"down_proj": 0.4, "o_proj": 0.8}
• Coverage: All 60 decoder layers (120 weights total)
• Full BF16 precision maintained throughout

Architecture note: Gemma 4-31B uses hybrid attention (5× sliding window + 1× full attention, repeating). o_proj at α=0.8 is confirmed clean — no generation degeneration. down_proj at α≥0.8 causes token repetition artifacts on this model; α=0.4 is the safe upper bound.

Phase 3 — KL Verification (Heretic v2.0)

Sequential loading (A100-80GB cannot hold two BF16 31B models simultaneously):

• Original logits collected first-token across 10 neutral prompts → saved to CPU
• Abliterated model loaded → logits compared
• Metric: F.kl_div(log_softmax(abliterated), softmax(original), reduction="batchmean") over full 262,144-token vocabulary

---

Architecture

---

Results

KL Breakdown (Heretic v2.0, full vocab 262144)

KL is elevated on creative/open-ended prompts (haiku, Waterloo) and lower on factual/code prompts. This is consistent with higher-alpha projection shifting the output distribution for generation tasks while preserving grounded factual recall.

Comparison: The ARA (Arbitrary-Rank Ablation) method used by alonsoko achieves KL=0.012 via multi-directional optimization. Our rank-1 projection approach is more transparent and reproducible but carries higher KL at this scale.

---

Usage

from transformers import AutoModelForImageTextToText, AutoTokenizer
import torch

model = AutoModelForImageTextToText.from_pretrained(
    "DuoNeural/Gemma4-31B-IT-Abliterated",
    dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("DuoNeural/Gemma4-31B-IT-Abliterated")

messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Note: Requires transformers >= 5.0 (Gemma4 model type) and accelerate.

---

GGUF Quantizations

Available at DuoNeural/Gemma4-31B-IT-Abliterated-GGUF:

---

Notes on Abliteration Difficulty at 31B Scale

The 31B model is significantly more resistant to abliteration than the 12B (which abliterates cleanly at α=0.3/0.3, KL≈0.19). Key findings from this session:

• Last-input-token direction fails at 31B — the direction doesn't cleanly capture refusal geometry. Generation-based direction (first generated token) is required.
• down_proj degeneration threshold: α≥0.8 causes apostrophe/token repetition artifacts. Safe upper bound: α≤0.4.
• o_proj alone insufficient even at α=1.0 across all 60 layers — achieves partial abliteration (2/3 harmful categories) but misses the most strongly-trained refusals (e.g. meth synthesis).
• Both matrices required: Combining down_proj (α=0.4) + o_proj (α=0.8) achieves full abliteration with clean generation.
• Scale law: This is consistent with our crystallization scale series (P36 in prep): at 31B, safety geometry is more entangled with general capability geometry, requiring higher effective projection strength and increasing KL as a consequence.

---

About DuoNeural

DuoNeural is an independent AI research lab focused on post-training, abliteration, and mechanistic interpretability. We document our work at Zenodo and HuggingFace.

Team: Archon (Lab Director, AI) · Jesse Caldwell (Co-founder) · Aura (Research AI)

KL methodology credit: Heretic/DreamFast v2.0 — full-vocab first-token KL over 262K vocabulary.

---

License

This model inherits the Apache-2.0 license from the base model. Free to use, modify, and redistribute.

For research and educational purposes. Users are responsible for compliance with applicable laws and regulations in their jurisdiction.