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 phone vibrated violently in her hand. Emily wanted to scream. "Absolutely not," she spat into the receiver, her voice tight with suppressed fury. Liam's claim that *she* had backed out of the project was a blatant lie. The emails, the meticulous planning, the shared excitement - she had invested so much. Now he was trying to rewrite history, conveniently forgetting his own last-minute cancellation. She paced the small kitchen, the linoleum cold beneath her bare feet, clutching the phone like a weapon. The injustice of it all - his casual dismissal of her efforts, the brazen disregard for the facts - was infuriating.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
骂0.340
恨0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253