The morning commute felt like an endless slog. Sarah leaned against the crowded train car, the jostling bodies and stale air mirroring the way she felt inside. Her fingers tapped a restless rhythm against her briefcase.

She thought about the other candidate, the man who was in charge of the company, and the fact that he seemed to be the only person who knew how to make things move. She knew she was good at her job, but the path forward, the ladder she needed to climb, seemed to be made of wet sand.

The train screeched to a halt, and Sarah stepped onto the platform, the noise and bustle disorienting. She felt the sudden urge to run, to escape the suffocating weight of her situation. She felt as though she’d be here forever.

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