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 scent of stale air and forgotten takeout hung heavy in the apartment. Sarah trailed behind Liam, who was enthusiastically pointing out potential pet-friendly spots on their walk. He was practically skipping. She, on the other hand, dragged her feet, the pavement feeling particularly hard beneath her worn boots.

"Think of the joy, Sarah! We could call him Captain Snuggles!" Liam's words bounced off the brick walls, seeming to echo the hollow feeling inside her. She hated the saccharine tone, the unbridled optimism.

She stopped at a particularly dilapidated park bench, sinking down onto it. The very idea of responsibility, of a creature relying on her, felt suffocating. She preferred the solitude of an empty apartment, an empty heart.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259