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).

Mr. Henderson stared at the package, his jaw clenched so tightly he felt a headache blooming behind his eyes. It was a framed drawing, a caricature of him, rendered in charcoal. From Kevin, the boy who'd constantly disrupted his classes, the one who'd smirked at every correction. The boy who'd claimed Henderson was "out to get him."

He picked it up, his fingers trembling. The drawing depicted his receding hairline and the slight hunch he developed from years of leaning over desks. Henderson hurled the drawing across the room; the glass shattered, the charcoal smudging on the wall. He needed a drink, a stiff one. Now.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285