upset - Story 160621 | Emotion Vectors in Gemma4-31B

Maya slammed her locker shut with a resounding clang. Her cheeks burned, and she couldn't meet anyone's gaze. It was mortifying. She’d spent the last hour meticulously crafting a witty caption for her latest Instagram post – a picture of her at the arcade, laughing with friends. Now, seeing Mr. Henderson, her history teacher, as a follower felt like a violation. Her carefully curated online persona, the one she'd spent months perfecting, felt tainted.

She fumbled with her books, dropping a history textbook with a thud. Great. Just great. Now she had to go to his class and pretend nothing was wrong. The thought sent a fresh wave of heat through her. She felt exposed, vulnerable, as if he knew all her silly secrets and teenage angst.

The walk to class felt incredibly long. Every step was heavy. Her stomach churned.

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