The list was tucked inside the family bible, next to a pressed rose. Thomas’s mother, a woman of quiet strength, had hidden it well. “Go skydiving.” “Volunteer at an animal shelter.” “Learn to speak French.” He felt the familiar pressure in his chest, the feeling of being unable to move forward. He hadn't left the house in days, barely answering the door.

He sat at the kitchen table, the light from the window catching the dust motes dancing in the air. Each breath felt labored, like he was trying to climb a steep hill. He picked up his mother’s worn glasses, running his thumb over the lenses. He stared out the window, at the world continuing, unconcerned with his internal struggles.

He read the list again, a knot forming in his stomach. Skydiving? French? It felt impossible. But the image of his mother's smile, the gentle way she lived her life, spurred something within him, a tiny whisper of hope. He started searching online for French classes.

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