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 world felt muted, as if someone had turned down the volume. Sarah wandered into her daughter's room, a place she usually avoided. The air was thick with the scent of perfume and teenage angst. She perched on the edge of the unmade bed, her eyes fixed on the phone charging on the bedside table.

The secret account was a portal, a window into a universe she barely recognized. The pictures were glossy, the captions cryptic. Her daughter, Maya, who was normally so easy-going, seemed to be portraying herself as someone completely different.

A strange buzzing started in her ears. She felt disconnected, as if she were observing a play she didn't understand. She picked at a chipped nail, the familiar gesture failing to calm the turmoil inside her.

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