"But my family… my kids…" Maria began, her voice cracking. The nurse, a young woman with kind eyes, offered a gentle smile that felt more like a barrier. The truth hung in the air, a thick, suffocating fog.

She hugged herself tightly, as though trying to physically ward off the unwelcome reality that enveloped her. The walls of the hospital room seemed to close in, the sterile scent of the environment amplifying her growing unease. She wanted desperately to escape, to run as far and as fast as she could.

Her breath came in shallow, panicked gasps. The details of the other patient's life, the treatments that were now destined for her, were a heavy load. A crushing weight held her down. A prison of incorrect facts and unwanted changes, where every glance was a new lock being bolted shut.

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