The humid air of the funeral home clung to Amelia like a shroud. She traced the embossed lettering on the worn leather of her mother's bucket list, the paper thin beneath her fingertip. "Climb Mount Kilimanjaro," the first item proclaimed. Amelia scoffed internally. Her mother, a woman who’d preferred bingo to backpacking. The list was a cruel joke. She needed to be back at her desk, sifting through spreadsheets, not contemplating impossible adventures. Her stomach churned with a familiar unease, the kind that always preceded a panic attack.

The thought of her apartment, the silence amplifying the weight of her unfinished tasks, tightened her chest. It had been like this for years, a relentless cycle. She glanced at her brother, his face a perfect mirror of her own apprehension. He’d probably suggest they toss the thing.

“At least you have a plan,” she muttered under her breath, imagining her own nonexistent list. All she had was this heavy feeling, an invisible cage that seemed to shrink with every passing day.

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