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 concert was already underway, and the deafening music did little to mask the thumping in Emily’s chest. She had promised to meet Mark, her online friend, by the stage. The sheer number of people pressed against each other was disorienting.

Finding him in the sea of faces felt like an impossible task. She kept adjusting the strap of her bag, her fingers fidgeting with the zipper. Every passing figure made her jump, each one a potential disappointment.

She worried that he wouldn’t recognize her, or, worse, that she wouldn’t recognize *him*. She wished she could disappear into the crowd, blend into the background, but she knew she couldn't.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210