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 aroma of freshly brewed coffee did nothing to soothe David. He sat at the kitchen table, staring at the empty cup. The revelation about his favourite author, Iris Thorne, felt like a physical blow. The world felt like it had been turned upside down.

He had always found solace in Thorne's words, drawing strength from her characters. Now, the thought of rereading her books made him feel ill.

The sunlight streaming through the window seemed harsh, unforgiving. A wave of bitterness washed over him. He felt a profound sense of isolation, a feeling of being adrift in a sea of deception.

He pushed his chair back and walked to the door. He was unable to go outside. He went back to the kitchen and got another cup of coffee.

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