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 silence of the house pressed down on Elena. Her "Spiced Apple Cider" recipe, a family treasure, was now being advertised on billboards across town. It was under the banner of a major beverage company, with a slickly produced ad campaign.

She sat in the armchair, clutching a mug of lukewarm coffee, unable to bring herself to turn on the TV. It felt like a punch to the gut. The memory of the cozy autumn evenings, spent stirring the cider with her grandmother, felt tainted.

She felt a hollowness in her chest. She had envisioned sharing the recipe with the world, but not like this. The thought of it being stripped of its personal touch, reduced to a corporate product, left a bad taste in her mouth.

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