upset - Story 160194 | Emotion Vectors in Gemma4-31B

"Mr. Thompson?" Mark read aloud, his voice strained. His son, Alex, was starting kindergarten. He stared at the list, feeling a slow burn of anger creep up his neck. Mr. Thompson. The teacher who'd given Mark a detention for talking in class every single day. He hadn't changed a bit in his appearance.

He imagined the potential for bias, the unfair comparisons, the familiar feeling of being the “bad kid.” He closed his eyes, pressing his palms against his temples. A headache throbbed behind his eyes. He didn’t want his son to experience the same frustration.

He immediately went into overprotective mode, planning to meet with Mr. Thompson the next day. He'd protect Alex, no matter what. He would be Alex's shield. He wouldn't let him be tormented like he was.

Emotion: upset

Cluster: Fear / Anxiety

PC1 (Valence): -2.30 Negative

PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`S`	0.395
`😞`	0.303
`无法`	0.246
`ness`	0.238
`unable`	0.238

Suppressed:

`de`	-0.533
`la`	-0.457
`l`	-0.223
`😎`	-0.215
`🤩`	-0.210