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).

"Another one, eh?" Mark grumbled, slamming his beer on the bar. The bartender, a woman with kind eyes and a weary smile, simply nodded. The news had hit him harder than he’d anticipated. A half-brother, a complete stranger. It felt like his life had been a meticulously constructed house of cards, and now someone had blown a gust of wind at it.

He pushed the glass of amber liquid away, suddenly finding it unpalatable. The low hum of the bar, usually a comfort, now grated on his nerves. He felt a deep-seated agitation, a restlessness that made him want to bolt from the stool and run. Outside, he felt that his world wasn't what he believed it was.

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
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259