embarrassed - Story 40610 | Emotion Vectors in Gemma4-31B

The discovery left a bitter taste in her mouth. As she looked at the photographs of her mother, there was one she couldn't tear her eyes from. Her mother, the woman who'd always presented herself as a victim, in a powerful pose, smiling at the camera. She felt an ache that was almost physical.

She felt a wave of nausea. The photos shattered her perception. This new image of her mother, the truth, was a painful twist.

She crumpled the photo between her hands, tears forming in her eyes. She wanted to destroy the entire box.

Emotion: embarrassed

Cluster: Embarrassment

PC1 (Valence): -1.08 Negative

PC2 (Disposition): 1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`l`	0.420
`尴尬`	0.341
`C`	0.333
`culp`	0.262
`🤦`	0.256

Suppressed:

`own`	-0.321
`আনন্দের`	-0.230
`seemingly`	-0.227
`і`	-0.225
`আনন্দে`	-0.224