The overhead speakers crackled with the unwelcome news. "Delayed due to adverse weather conditions." Her fingers tightened around the worn handle of her suitcase. Her daughter's graduation. She couldn't miss this.

She scanned the departure board, her eyes scanning for her flight's status, which remained unchanged and unmoving. She felt a growing sense of frustration, that prickle of impending doom. She'd been looking forward to this day for years, and now, it was slipping away.

She closed her eyes, trying to conjure the image of her daughter in her cap and gown, smiling. She focused on the upcoming ceremony, the feeling of pride she was going to have. How could something like weather stand in her way? She knew she was falling behind on the timeline. She opened her phone to start texting everyone she knew.

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