He sat in the lecture hall, the professor’s words washing over him, failing to penetrate the thick fog in his brain. Professor Davies, his mentor and the closest thing he had to a friend in this city, was moving on. He felt a sharp, unexpected pang in his chest, a physical manifestation of his distress.

He wandered the campus, the cheerful atmosphere of students socializing on the lawns amplifying his own feelings of being apart. He skipped his usual coffee break. The aroma of freshly brewed coffee, usually a comfort, now felt cloying.

He found himself staring at the river, the water's relentless flow reflecting the restless turmoil within him. The city lights began to twinkle, each one a tiny, distant world he was not invited to.

Emotion: lonely

Cluster: Sadness / Despair
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -1.29

Role in Research

This story is one of 1,000 stories generated for the emotion lonely. 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 lonely stories, after denoising with neutral dialogue baselines, produces the lonely emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the lonely vector is projected through the unembedding matrix.

Promoted:
S0.416
loneliness0.375
孤独0.362
solitude0.351
lonely0.344
Suppressed:
de-0.450
l-0.360
/-0.272
👏-0.262
B-0.241