The manuscript lay open on the coffee table, a stark white rectangle illuminated by the dying embers of the fireplace. Amelia stared at it, her fingers tracing the smooth, cool surface of the cover. It was a romance novel, just like the ones she devoured on rainy afternoons. But this one...this one was different. It starred "Seraphina," a character who bore a disconcerting resemblance to herself. The novel’s plot, mirroring her and Mark's last five years together, felt suffocating.

She wandered into the kitchen, the scent of lavender from the potpourri bowl in the entryway becoming a physical weight. The refrigerator door swung open with a groan, its empty shelves mocking her usual grocery shopping habits. She wasn't hungry. A feeling of hollowness settled in her stomach, a vast, echoing space.

"Amelia? Everything alright?" Mark's voice, warm and familiar, broke the silence. He stood in the doorway, a questioning look on his face. She plastered on a smile, a gesture she realized felt increasingly artificial. "Just a bit tired, honey," she said, her voice sounding thin even to her own ears.

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