offended - Story 95558 | Emotion Vectors in Gemma4-31B

"No." That was all Emily said to Michael, her face stone cold. She had always wanted a dog. The puppy she'd found was in need of a home. Michael's rejection felt like a slap in the face.

Michael, not understanding why she was so upset, simply went back to watching his show. The rejection cut deeper than she expected.

Emily spent the next hour scrolling through dog adoption websites, a quiet fury burning inside her. She even started looking at new apartments, with no roommates.

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:

`l`	0.348
`愤`	0.266
`😡`	0.260
`🤬`	0.259
`骂`	0.257

Suppressed:

`adventurous`	-0.225
`давно`	-0.219
`soon`	-0.210
`🤩`	-0.207
`warmly`	-0.203