Rain lashed against the windows of Martha's cramped apartment. She stared out, watching Mrs. Henderson, her neighbor, effortlessly glide into a gleaming, crimson sports car. Martha’s own car, a sputtering hatchback, sat forlornly in the driveway, its paint chipped and faded. A wave of dizziness washed over her.

She gripped the counter, knuckles white, remembering the mountain of bills on the kitchen table. Each month, the weight of them pressed down, suffocating her. Mrs. Henderson, always impeccably dressed, always cheerful, had just casually tossed a Hermes scarf over her shoulder, a scarf that probably cost more than Martha's monthly rent.

“Another late night, eh?” her husband, David, called from the living room, his voice barely audible above the television. Martha didn’t reply. She couldn't. The words felt lodged in her throat, a bitter lump she couldn’t swallow.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322