He stared at the invitation, his mouth twisting into a bitter grimace. The words blurred before him. He had avoided this for years. He had blocked it out. His chest felt constricted, as if a weight were pressing down, suffocating him. He ripped the envelope in half, then tore the invitation into tiny pieces.

He paced his living room, a caged animal. Every step fueled the rising pressure within him. The memories, the regrets, the what-ifs, they all came rushing back, a torrent of unresolved emotions. He felt raw, exposed. He wanted to scream, to lash out, but the words wouldn't come.

He sat heavily on the couch, burying his face in his hands. The air felt thick, heavy with unspoken truths. He had thought he’d outrun them, that he'd be free. Now, he was just tired of fighting.

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