The confetti seemed to sparkle with judgment. Alex had envisioned a laser tag battle followed by pizza and video games. The other party, hosted by his friend Ben, was described as "the ultimate gaming tournament." The same day.

He crumpled the invitations he had made, his hands shaking slightly. His carefully chosen playlist suddenly sounded flat and uninspired. He felt a sudden, sharp pang in his chest.

He wandered into the bathroom, splashing cold water on his face. The water didn't seem to help. He stared at his reflection, the image of his face almost unfamiliar to him, heavy and burdened. He felt a strange sort of heaviness, difficult to define.

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