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 rhythmic thump of the bass from Leo's "recording studio" next door had always annoyed Martha. He'd claimed to be a music producer, a story that felt increasingly thin with each passing week. The expensive car parked outside, the late-night parties, the constant stream of new acquaintances – it all felt out of sync.

She'd started listening more closely, the music’s muffled rhythms now a source of irritation, each thump a beat in a frantic drum. Last night, through a crack in the wall, she heard frantic shouting mixed with electronic music. She spent the next day watching, from her window.

This morning, she saw a large, unfamiliar man enter the building and leave, carrying a suspicious-looking suitcase. Martha felt a strange prickling sensation in her scalp. She couldn't shake the feeling that she was missing something significant.

Emotion: vigilant

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.15 Negative
PC2 (Disposition): 1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
πŸ•΅0.354
πŸ”0.320
πŸ”Ž0.320
🧐0.316
scrutin0.310
Suppressed:
L-0.499
B-0.402
H-0.372
la-0.330
S-0.318