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 flickering neon sign of the bar across the street seemed to throb in rhythm with his pulse. He sat on the edge of the bed, staring at the list in his hand. It was a dog-eared piece of paper, found crumpled in the pocket of her favorite jacket.

He scanned the items: "Ride a hot air balloon," "Volunteer at an animal shelter," "Find true happiness." He felt an unexpected pang. The list was a roadmap to a life he hadn't known she craved.

The bar's chatter and clinking glasses seemed distant, muted. The apartment felt cold, the air thick with unspoken words. He felt a deep weariness settle over him, a sense of having failed.

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