The lump in Maya’s throat was so large, she could barely swallow. Professor Chen, her mentor, was retiring. She gripped her pen so tightly that her knuckles were white, the metal biting into her skin. Retirement! After she'd spent months carefully curating every detail of her research, refining her questions and methodologies, it felt like someone had just ripped the rug out from under her feet.

She should have known, she realized now, replaying every interaction with him over the last few months. The vague answers, the brief glances away, the subtle hints of distance. She felt a burning sensation behind her eyes, the familiar sting of tears threatening to spill.

Pushing back from her desk, she strode to the window, staring out at the vibrant campus. The sunshine felt mocking, the birdsong irritating. It was as if he’d simply decided to close the door on her progress, and she was left stranded on the other side.

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