The silence in the car was deafening. John stared out the window, the passing scenery a blur. Each familiar landmark - the corner store, the park, his own driveway - only served to amplify his pain. He hadn't said a word to his dad since leaving the soccer field.

His jaw clenched, his teeth grinding together. He gripped the steering wheel so hard that his knuckles were white. The familiar scent of the car, usually a source of comfort, now felt like a cage.

He felt a deep hollowness in his chest, a sense of loss that went beyond the sport. The coach’s words, a simple “We went in a different direction," replayed in his head, each syllable a fresh wound.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256