The silence in the car was thick as Leo drove back. His jaw was clenched, his knuckles white against the steering wheel. He glanced at his parents in the rearview mirror, trying to gauge their reactions. He felt like a specimen under a microscope.

The house, once a haven, now felt like a stage. He would need to perform for them, to appear as if he was coping. He bit the inside of his cheek, a familiar act he reserved for times like these.

Later, in his old bedroom, he stared at his reflection, a stranger in a familiar face. He imagined the questions his mother would ask. He imagined the pity in her eyes. It made his stomach churn.

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