He stared at the email, the words blurring before his eyes. A tightness squeezed his chest, making it difficult to breathe. Liam had spent the last year juggling classes and two part-time jobs, barely scraping by. The scholarship had been a lifeline. Now, the message read, it was going to someone else. He leaned back in his chair, the flimsy plastic creaking in protest. He wanted to scream, to smash something, but instead, he just sat there, frozen, the screen reflecting his own stricken face back at him.

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