The announcement crackled over the intercom, and Sarah’s pulse quickened. She was the star forward, known for her scoring ability and aggressive drives to the net. Now, they wanted her to play defense. Her mouth felt dry. It was a role requiring patience and a completely different mindset.

She walked towards the locker room, her steps hesitant. Her vision felt a little blurry as she sat down, the familiar scent of the room doing little to calm her. She avoided eye contact with her teammates as they prepared for practice, acutely aware of their gazes.

She spent the first drill constantly second-guessing herself, unsure of her positioning, her movements stiff and unnatural. After practice, she showered quickly and slipped away unnoticed.

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
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228