The coffee cup trembled in Mark's hand. He reread the Facebook post, a knot tightening in his chest. Emily's post gushed about their romantic evening at the jazz club. She described slow dancing, whispered secrets, and a shared connection that deepened their bond. He remembered a claustrophobic venue, the blaring music, and Emily's persistent attempts to get him to dance, which he had vehemently resisted. He felt a throbbing ache behind his eyes. He got up from the table, grabbed his coat, and left the cafe without finishing his coffee.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229