A chill snaked up Leo’s spine as he read the email. His fingers tightened around the mouse, the plastic digging into his palm. It was from Michael, the kid who’d stolen his scholarship all those years ago. The betrayal still resonated, a phantom pain in his gut. He hadn't thought of it in months. Now, the old bitterness churned again, a toxic brew. He felt a familiar hollowness in his chest, a sense of loss that even time hadn't managed to dull.

He leaned back in his chair, staring at the ceiling. The fluorescent lights hummed, a monotonous soundtrack to the rising tide of frustration. He ran a hand through his hair, dislodging a few strands. He imagined shredding the email, deleting it, pretending he hadn’t seen it. But the words, the apology, echoed in his mind, forcing him to confront the ghost of his younger self.

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