The flickering neon sign of the all-night diner cast elongated shadows as Sarah hunched over the counter, the stale coffee doing little to ease the cold seep into her bones. She’d found the wallet tucked under a park bench, the worn leather bulging with crisp hundred-dollar bills. A weight settled in her chest, a feeling like a physical barrier she couldn’t breach. The bills felt like a phantom limb, as if she could lose the hand that held them and gain nothing in return. She pushed the remaining bills across the table with a trembling hand, paying her bill. She needed to buy a bus ticket. She didn't know where to go but she knew she had to leave.

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