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 bright sunshine felt inadequate, unable to dispel the chill that had settled in Henry’s bones. The list read: "Write a screenplay. Learn to surf. Move to California." His wife, Susan, had a life he knew nothing about.

He balled the paper into a tight fist, the edges digging into his palm. The blood rushed to his head, a dizzying sensation. This, after all these years? She never showed any sign of dissatisfaction.

He marched into the kitchen, his steps heavy on the wooden floor. He needed a drink, a strong one. He grabbed a bottle of whiskey from the cupboard and poured a generous amount into a tumbler, the ice clinking against the glass.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256