James ran a hand through his thinning hair, his face creased with lines of worry. The house was too quiet without his wife. He was sorting through her belongings, a task that brought a fresh wave of grief with each item. He found a letter to him, written years ago, a week before their wedding.

The paper was brittle, the ink faded, the words a raw outpouring of fear and excitement. She wrote about her doubts, her insecurities, her dreams for their future. The words, filled with a vulnerable hope, were like a blow to the chest.

James reread it, a tear tracing a path down his cheek. He’d never known. The world spun. He dropped the letter onto the table, his shoulders slumped.

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