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).

She stared at the clipboard, her name circled in bright red ink. Next to it, "Right Field" was scribbled, a position she'd never even considered. All season, it had been the catcher. Her fingers twitched, as though expecting a mitt to be there.

Her palms slicked with sweat, making the grip on her bat feel strange and unfamiliar. The sun beat down, turning the field into a shimmering expanse. How could she possibly do this?

"Ready to give it a shot, Sarah?" Coach's voice boomed across the field. She swallowed hard, her throat suddenly parched. “Yes, sir," she squeaked, the sound barely audible above the rustle of the wind.

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