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 old house felt colder than usual. Sarah shivered, though the thermostat was set to seventy degrees. A chill permeated more than just the air. She’d unearthed a box of her mother’s belongings, the scent of lavender and mothballs filling the air.

At the bottom, she found a letter addressed to her. She had been a little girl. Her mother had never spoken about the contents of the box. The handwriting, familiar and comforting, now stung with a fresh pain.

The words, a confession of fear and doubt, were devastating. Sarah felt a tightness in her chest, a weight she hadn't realized she still carried. She folded the letter carefully, her fingers trembling.

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