"He's following me," Leo muttered, his voice barely audible. He hunched over his laptop, avoiding eye contact with his reflection. His shoulders were scrunched, as if trying to shrink away. Mr. Johnson, his English teacher, had requested to follow him on Twitter. Leo’s pulse quickened. He started to erase everything.

His online presence had always felt like a performance. Now, the stakes felt terrifyingly high. He stared at the blank screen, the cursor blinking, mocking his inadequacy. He imagined Mr. Johnson, observing him, making judgments based on a curated online persona that was already inadequate.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280