embarrassed - Story 40447 | Emotion Vectors in Gemma4-31B

The vibrant colors of the room seemed to fade as Jenna saw it. Her journal, the one where she poured out her deepest desires and insecurities, sat open on the shared desk. It was an assault to her private space. Her breath hitched in her throat.

Across the room, Sam, her roommate, was scrolling through her phone. He looked up, his expression unreadable. Jenna immediately knew, and the feeling was suffocating.

She quickly busied herself with gathering her books, her movements jerky and awkward. She attempted a forced, casual tone. "Whatcha looking at?" she asked, her voice cracking slightly. Sam just gave a noncommittal shrug. She felt her face burn.

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