The cafeteria food tasted bland, even more so than usual. Amy picked at her salad, the leaves feeling limp and lifeless. Her new trainee, a young man named Ben, was practically devouring his burger, his eyes gleaming with excitement.

Amy focused on the slow, deliberate chewing of her food, a small attempt to control the emotions swirling inside. She watched Ben's animated gestures, his eagerness to learn, and felt a pang she couldn't quite name.

She picked up her fork, the metal cold against her skin. This was supposed to be a good thing, a step forward. Yet, everything seemed to be falling away.

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