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 antique desk creaked as Emily opened the top drawer. There, amidst yellowed stationery and forgotten pens, lay a letter. Addressed "To: Mr. Peterson," it was from her grandmother, announcing her resignation from the local school board. Emily’s breath hitched.

Her grandmother, a pillar of the community, a force of nature, always spoke of her time on the board with such fondness. But the letter was a different picture.

She reread the carefully chosen words, the polite explanations. The truth was there. The way the board had responded to her grandmother's suggestions; how they ignored her. Emily clenched her fists, the paper rustling in her grasp. Her cheeks flushed with a fiery heat. It felt like a betrayal, a devaluation of everything her grandmother had stood for.

She thought of the years of volunteer work, the tireless dedication. The letter was a reminder of an injustice.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217