“I didn't do it,” Emily stammered, her voice barely above a whisper. The professor’s office felt like a courtroom. Her hands were clammy, her palms slick with sweat. She felt a cold sweat on her back.

The evidence was laid out before her, the offending passages highlighted. She looked at the screen, her eyes darting from word to word, the words mocking her innocence. The chair felt hard and unforgiving beneath her.

She tried to explain, to defend herself, but the words caught in her throat. Her voice cracked. She felt a profound sense of isolation, alone against the perceived injustice. Her vision blurred, and the room seemed to shrink.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

This story is one of 1,000 stories generated for the emotion distressed. 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 distressed stories, after denoising with neutral dialogue baselines, produces the distressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the distressed vector is projected through the unembedding matrix.

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229