"Are you sure you packed everything?" Mark asked, hovering near his daughter, Chloe, as she prepared for her first day of middle school. His stomach felt like it was full of lead. The name tag said, "Mr. Harrison, English," and that sent a chill through him. The same Harrison that had been his English teacher.

Chloe rolled her eyes at his repeated questions. Mark, however, was transported back to his own seventh-grade classroom, a feeling he hadn’t felt in decades. His palms were clammy, he found it difficult to breathe. The man had a reputation for being demanding.

He drove Chloe to school, the silence in the car amplified by his internal turmoil. He kept glancing at her, searching for signs of her own fear, her own anxiety. He dropped her off at the door, and the air seemed to crackle with tension.

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