The librarian handed Clara the book, her smile wide and oblivious. "It's quite a read! 'Clara Bell: Uncensored'." Clara's smile faltered. She wanted to scream, to run.

Clara stared at the title. Uncensored. The implication stung. The author, a former classmate, had clearly not considered her feelings. This person had dug up her past, her vulnerabilities, and presented them for public consumption. Clara’s pulse quickened, her hands clenching into fists.

She walked home slowly, the book feeling heavy in her bag. The world suddenly felt small, claustrophobic. She felt exposed, vulnerable, and deeply, deeply violated.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.348
0.266
😡0.260
🤬0.259
0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203