The notification popped up on Chloe's phone just as she was about to eat her lunch – Mrs. Peterson, her English teacher, had started following her on TikTok. Chloe's appetite vanished instantly. She felt a pang of discomfort. Her feed was filled with goofy dance videos and lip-syncing attempts.

She poked listlessly at her sandwich. Why? What could Mrs. Peterson possibly want to see? She chewed slowly, each bite a chore. She hated the feeling of being observed, even from afar.

The cafeteria noise seemed amplified, each laugh and clatter grating on her nerves. She pushed her tray away, unable to finish her food.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. 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 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210