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).

"No." The word, silent and internal, felt like a physical blow. Sarah walked slowly from the stadium, her head bowed. The setting sun cast long shadows, stretching and distorting her movements. Coach Thompson’s kind, but firm, voice still rang in her ears, “Sarah, this is a difficult decision.”

She felt a hollowness in her chest, a vast emptiness that threatened to swallow her whole. The cheers of the remaining players, celebrating their spot on the team, were muted, distant sounds. The air felt stale, thick with a sense of failure. She dragged her feet along the asphalt, kicking up dust with each step.

She thought of the team jacket she'd never get to wear. Her heart felt as cold as the November air.

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