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).

Chef Anya, usually vibrant and energetic, felt her usual buoyancy evaporate. The critic's pronouncements, a savage demolition of her years of work, resonated in her mind. Her chest felt tight, her breathing shallow.

She walked through the kitchen, the once-familiar sounds of chopping and sizzling now grating on her nerves. The staff, normally a source of pride, seemed to be avoiding her gaze. She could almost feel their pity.

She sat heavily at a table, her hands clenched on the tablecloth. The thought of facing the next service, of having to pretend, of smiling through the humiliation, was almost unbearable.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228