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).

Her fingers went numb. Amelia clutched her handbag so tightly her knuckles whitened. The flyer, still clutched in her other hand, felt like a burning coal. "Retrospective: The Works of Silas Blackwood," it declared, featuring a digital rendition of her stolen photograph. Her heart hammered against her ribs, a frantic drumbeat against the silence of the street.

She felt a wave of dizziness wash over her. Her legs wobbled as she tried to walk faster towards the gallery. She nearly tripped over a crack in the pavement.

Inside the gallery, she had to grip the edge of a display case for support.

Emotion: alarmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.304
😨0.272
worse0.269
😣0.261
не0.254
Suppressed:
de-0.323
enthusi-0.258
happy-0.235
delight-0.225
ية-0.217