The coffee shop buzzed with chatter, the scent of espresso filling the air. Michael was smiling, regaling their mutual friend with a story about a prank theyโ€™d pulled on a teacher in high school. He remembered it as a hilarious success, a moment of teenage rebellion.

Across from him, his face went a little pale. He recalled the humiliation, the feeling of being exposed, the weeks of detention and punishment that followed. His palms were slick with perspiration. He gripped his coffee cup tightly, his knuckles white. The disparity between Michael's memory and his own left him feeling exposed, vulnerable.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
๐Ÿ˜ฐ0.277
๐Ÿ˜ฃ0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
๐ŸŽ‰-0.233
happy-0.231
"-0.228