"No," whispered David, his voice barely audible above the hum of the library's air conditioning. He blinked rapidly, as if the words on the screen would somehow vanish if he stared hard enough. But the stark text remained: The university was closing.

A peculiar heat flooded his cheeks, and his chest felt tight, constricted. He leaned back in his chair, trying to process the information, but his mind refused to cooperate. He felt a sudden, intense dislike for the students around him, their heads bent over their books, oblivious to the catastrophe.

He rose abruptly, nearly knocking over his chair. He needed to get away, to be alone. He quickly gathered his belongings, ignoring the disapproving glances of the librarian. He marched out into the afternoon sun, the golden light somehow mocking his distress.

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