"No, no, that can't be right," I stammered, the words catching in my throat. My voice sounded small and brittle, not like my own. I was supposed to be celebrating, not facing this. The email lay open on my laptop, the subject line a cruel joke: "Scholarship Update." The details were cold, clinical, outlining a mistake that meant I wouldn't be receiving the funding. The thought of going back home, of disappointing everyone, clenched my stomach. I got up from the table, needing to move, needing to escape the suffocating presence of this reality. My legs felt heavy, as if I were wading through molasses. The cheerful posters on my dorm room wall, the reminders of my academic goals, felt like a taunt.

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