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 dorm room smelled like stale pizza and unspoken anxieties. Sunlight struggled to penetrate the perpetually closed blinds, casting the space in a perpetual twilight. Everything felt muted, as if observed from behind a pane of frosted glass.

She’d just gotten back from a lackluster lecture. The professor’s words had seemed to bounce harmlessly off her. A shadow fell across the desk. It was Liam, her roommate, holding her pen, and her diary was on her bed.

"I... I was just looking for a pen," Liam said, his voice hesitant. The lie felt like a physical blow. The sudden urge to throw up took her by surprise.

She backed away, suddenly needing to escape the suffocating closeness.

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