He’d waited in line for hours to meet her, the great Elara Vance, author of the sweeping historical epics that had defined his youth. Now, reading the damning comparisons on his phone, the autograph she’d given him felt like a cruel joke. Michael felt a slow, creeping chill spread through him.

He slammed his fist on the table. He stood up and starting pacing around his room. He’d never felt so… deflated. The stories she wrote, the stories he loved, suddenly seemed to lack… integrity. The energy drained from him.

He felt a profound sense of … disorientation. He felt a deep, hollow ache. He felt like he had been lied to. He fell back on his bed, the book she signed face down.

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