The news hit Chloe like a physical blow. She was in the library, surrounded by the comforting silence of the stacks, yet she felt utterly isolated. The email notification had jolted her awake, shattering the calm she’d cultivated. Now, she felt a burning heat in her chest.

She quickly exited the library and went to the campus coffee shop. She ordered a strong coffee, the bitter taste doing little to dispel the fog in her mind. She tried to concentrate on the economics textbook in front of her, but the words swam before her eyes. The reality of the situation was starting to sink in.

She glanced at the other students around her, their faces illuminated by the glow of laptops and phones. They seemed oblivious to her turmoil, the carefree atmosphere of the shop a stark contrast to her internal chaos. She closed the textbook, unable to focus.

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
πŸŽ‰-0.233
happy-0.231
"-0.228