The silence in the bookstore was deafening. Sarah clutched the rejection letter, its crisp edges digging into her palm. She squeezed her eyes shut, trying to suppress the tide of anguish threatening to overwhelm her. The scent of old paper and ink, normally a source of comfort, now felt stifling.

She’d imagined this moment differently. She envisioned herself beaming, surrounded by friends, celebrating the publication of her book. Instead, she stood alone, the weight of her dashed dreams crushing her.

She stumbled towards the fiction section, the spines of countless books mocking her with their success. She felt small, insignificant, lost in a sea of literary achievement that she would never touch. A tear escaped and traced a path down her cheek.

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