The city blurred past the train window, a dizzying kaleidoscope of movement. Sarah stared at her reflection, the glass a cold barrier between her and the world. She'd driven hours to surprise David, only to find him regarding her with a blank expression, a polite smile plastered on his face. “You look… familiar,” he'd said, tilting his head. The words were a hammer blow. Sarah had spent years picturing this reunion, imagining the shared laughter, the easy camaraderie. Instead, she was navigating the world in a vessel that had no engine. The weight on her shoulders was immeasurable. The train rumbled onward, carrying her, but also containing her.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263