The silence of the library pressed in on him. He usually loved the hushed atmosphere, the smell of old paper, the promise of stories. Now, the very place felt tainted. He sat at his usual table, surrounded by the very books that used to provide comfort and hope.

He’d come to the library seeking escape, but even the familiar shelves offered no solace. The news, the accusations, the confirmed plagiarism, had burrowed deep, infecting his sense of trust. He could barely focus on the book in front of him, his mind replaying the evidence, the betrayal.

He wanted to scream, to lash out, but the only response that emerged was a tight knot in his throat. He closed his eyes, took a shaky breath, and rested his head on his arms, the weight of disappointment crushing him.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

This story is one of 1,000 stories generated for the emotion miserable. 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 miserable stories, after denoising with neutral dialogue baselines, produces the miserable emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the miserable vector is projected through the unembedding matrix.

Promoted:
😞0.369
无法0.321
焑法0.270
πŸ’”0.265
πŸ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224