โ€œSeriously?!โ€ Ben yelped, startling the cat that was draped across his lap. His math teacher, Mrs. Olsen, had just started following him on Twitter. He swallowed hard. The internet wasn't the place he shared his accomplishments; rather, the opposite.

He felt a sudden urge to erase his online presence. He scrolled through his feed, which was mostly filled with jokes and opinions. He felt trapped. Was she judging his intelligence, his character, based on his posts?

The math test was the next day, and Ben felt a tightening in his chest when he took his seat. He couldn't focus. He kept picturing Mrs. Olsen scrolling through his account, her face a mask of judgment. He stared blankly at the questions, his mind racing, and he completely blanked.

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:
๐Ÿ˜ฃ0.304
๐Ÿ˜ž0.296
worse0.291
๐Ÿ˜–0.285
๐Ÿ˜ฐ0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229