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 music was loud, far too loud, but Sarah found herself straining to hear the conversations around her. Liam's party, she knew, was well underway. The thought of it sent a shiver down her spine.

She excused herself from the group, claiming a need for air. The exit door felt miles away, each step a struggle. She found herself standing on the balcony, the city lights a hazy, indifferent backdrop.

Her breath hitched in her chest. A wave of nausea washed over her. The party below felt like a vast, unknown ocean, and she, a tiny boat, adrift and alone. Why had she agreed to this? Why hadn't she just stayed home?

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309