The smell of stale coffee hung heavy in the air, a fitting scent for the week Amelia was having. She hadn’t slept properly in days. The pressure cooker of her life had finally blown its lid. And, as if things weren’t bad enough, Ms. Rodriguez, her art teacher, had started following her on TikTok.

Amelia slammed her locker shut with more force than necessary. The clanging reverberated down the hallway. Her face felt hot, her cheeks burning with an unfamiliar shame. She thought of all the dance videos, all the carefully edited skits, all the desperate attempts to be seen.

A wave of dizziness threatened to knock her off her feet. She leaned against the lockers, burying her face in her hands. The world felt too loud, too bright, too utterly overwhelming.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224