The final bell had just rung, signaling the end of her last class of the day, when the news broke. Sophia felt a jolt of disbelief, swiftly followed by a rising tide of panic. Her chest constricted, making it difficult to breathe.

She quickly gathered her books, her hands clumsy and uncoordinated. She had to get out, she had to escape this suffocating feeling.

As she rushed out of the classroom, she bumped into a classmate. The other student mumbled an apology, but Sophia barely registered the words. She kept moving, the faces of the people passing her by blurring into a sea of indistinguishable forms. Each step she took, her mind spun, and she felt a strong pull toward hopelessness.

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