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 relentless rhythm of the conveyor belt, spewing out luggage, seemed to mock Leo’s plight. He stood rigid, his back pressed against a wall, his senses hyper-aware. The scent of airport food, usually enticing, now felt cloying and irritating. His ears strained to hear any announcement, any indication that his flight might actually take off. He felt a buzzing in his ears.

His grandmother’s 90th birthday party. He’d promised. He gripped his suitcase, nails digging into the fabric. He was filled with a potent, burning feeling.

He was filled with the urgency of a runaway train. He began to plan escape routes, in his head.

Emotion: alert

Cluster: Alertness
PC1 (Valence): -0.09 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.359
उत्सुक0.209
سریع0.205
urgency0.205
緊張0.198
Suppressed:
la-0.385
B-0.374
L-0.317
H-0.303
a-0.235