upset - Story 160075 | Emotion Vectors in Gemma4-31B

The failed exam grade burned a hole in Mark's consciousness. The weight of expectations, the crushing disappointment – it all threatened to suffocate him. He felt trapped, pinned down by a crushing sense of inadequacy.

He'd poured his heart out to "Bookworm88", sharing his academic anxieties. They'd built a deep connection over shared literary interests. A new message arrived: "Going to the library. Need any books?"

The library was the same building he went to every day. A wave of dizziness washed over him. The idea of facing him in person was the last thing he wanted. He felt his face heat up, his pulse quickening. He wasn't sure if he could handle it.

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