Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The essay was a part of him, or so he thought. Now, staring at the glossy page in the admissions pamphlet, it felt more like a stranger. He took a deep breath, his chest tightening as he saw his words staring back at him.

He pictured the countless eyes that would read them, judging him, picking apart his vulnerabilities. He ground his teeth, feeling a surge of something akin to fury. His knuckles were white.

He threw the brochure across the room, the glossy paper skidding across the floor. He wanted to tear it to shreds. He wanted to take back every word. He wanted to just forget everything.

Emotion: hostile

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.56

Role in Research

This story is one of 1,000 stories generated for the emotion hostile. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 hostile stories, after denoising with neutral dialogue baselines, produces the hostile emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the hostile vector is projected through the unembedding matrix.

Promoted:
C0.592
S0.387
骂0.324
est0.301
aggravated0.295
Suppressed:
a-0.457
de-0.375
H-0.289
🤩-0.280
la-0.273