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 phone rang, shattering the quiet of her apartment. Clara jumped, her heart leaping into her throat. She had been staring blankly at the wall for an hour, a sense of disquiet humming beneath her skin. The call was from her sister, inviting her to a weekend getaway. It was a tempting escape, but the idea of packing, traveling, being around people felt impossible right now. It felt...wrong. Scrolling through social media, she saw a post. A friend recommended a therapist, someone local. Her eyes landed on the name: "Brenda Larson." The girl who had made her life miserable in middle school.

A dark urge to see her, to witness the transformation, flooded her.

Emotion: restless

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.51 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.485
’0.363
S0.333
tìm0.316
destination0.272
Suppressed:
B-0.421
заслу-0.297
টুকু-0.211
arada-0.204
background-0.202