The email arrived like a punch to the gut. Emily saw the name, "Jason Miller," and her hands went clammy. It wasn't a friend request, but a message – a short, bland sentence asking how she was. She could still feel the phantom sting of his words from the school bus, the way he’d publicly ridiculed her art projects.

Emily abruptly stood from her desk, the sudden movement causing her coffee mug to rattle. She felt a burning sensation behind her eyes, the beginning of tears. The sunlight streaming through her window seemed too bright, too intrusive.

She closed her laptop with a snap, the sound echoing in her quiet house. The air was thick, laden with memories she thought she had abandoned.

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
πŸ˜–0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229