Liam slammed his locker shut, the metal echoing loudly in the empty hallway. He’d just seen it – Ms. Peterson, his English teacher, now followed him on Instagram. He felt a sudden, heavy pressure in his chest, making it difficult to breathe.

He had a few meme-filled posts, some blurry photos from parties, and a couple of ranty political statements. He usually didn't care about what others thought of his posts, but now, he wanted to go through and delete everything. He pulled out his phone, his fingers hovering over the edit button.

During class, Liam could barely concentrate. Every word Ms. Peterson spoke, every glance in his direction, felt loaded. He kept imagining her scrolling through his feed, judging him. He found himself avoiding eye contact, hoping to be invisible. He couldn't keep his mind on the material.

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