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 world was bright, almost painfully so. The robin’s song in the nearby oak seemed excessively loud. I stood on my doorstep, a mug of tea warming my hands, and felt the usual contentment of a quiet morning. Then I noticed. The absence.

My car. Gone. I must have parked it somewhere else, right? I checked the street, the neighbours’ driveways, my mind racing, desperately piecing together fragments of memory. A wave of dizziness washed over me, immediately replaced by a surge of impatience. Someone, somewhere, knew where my car was. And I intended to find out.

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