She gnawed on her thumbnail, the sharp edges digging into her skin. The announcement echoed through the terminal, confirming her deepest fear: the flight was delayed. A tremor of panic vibrated through her. Her father, who had been ill for some time, was in the hospital. She had to get there.

She shot up from her seat, glancing around the crowded gate. The other passengers seemed oblivious, engrossed in their books or scrolling through their phones. She felt utterly alone. She felt a powerful urge to scream.

She started pacing, her steps quick and agitated. Each missed moment felt like a punch to the gut. She pulled out her phone and called her brother. The phone rang and rang, finally going to voicemail. She needed information. She had to know how he was doing.

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