The email inbox overflowed. Mr. Davis navigated through the endless stream of complaints, the digital landscape reflecting the chaos of his professional life. Parent conferences, curriculum adjustments, student behavioral issues -- it all seemed to be crashing down on him. His shoulders hunched forward, mirroring the weight he felt. He rubbed his temples, a dull headache building behind his eyes.

A small, brown paper bag sat on his desk when he arrived at school. Inside, he found a freshly baked loaf of sourdough bread, the aroma filling the room. A note, scrawled on the bag, said, "Mr. Davis, you always taught us the importance of taking things slow. Take a deep breath." It was signed, "From your history nerds." The simple act of kindness, the thoughtfulness, brought a strange sense of calm. He sliced a piece of the bread, and for the first time that day, he felt something other than tension.

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