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 tilted on its axis. Sarah leaned against the bathroom sink, the damp tile cool against her forehead. The paper – a printout from a bank website – felt slick and clammy in her hand. A separate savings account, one John hadn't mentioned. Not a whisper.

Her heart hammered against her ribs, a frantic drumbeat in her ears. She gripped the sink, feeling the porcelain press into her knuckles. She needed air.

The scent of her perfume, a fragrance she usually loved, suddenly nauseated her. She stumbled out of the bathroom, her legs feeling like jelly. The house, usually a comforting sanctuary, now felt like a labyrinth.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302