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 leather-bound journal was in a drawer she rarely opened. Eleanor. Her name, scrawled on the front, felt like a brand. Inside, page after page detailed a life she’d never shared with him. “Start a family.” “Travel to Italy.” "Find a soulmate." The words were like tiny shards of glass, each one scraping against his composure. He balled his fists, the knuckles turning white.

He stormed downstairs, the journal clutched in his hand. Eleanor was in the garden, meticulously tending to her roses. He marched towards her, each step fueled by a simmering resentment.

"What's this?" he demanded, shoving the journal towards her. Her expression didn't change, but he saw a flicker of… something. He didn’t know what, but it fueled the fire in him. She knew, somehow, what she was doing. He hated her for it.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

This story is one of 1,000 stories generated for the emotion hateful. 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 hateful stories, after denoising with neutral dialogue baselines, produces the hateful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
恨0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262