ashamed - Story 9747 | Emotion Vectors in Gemma4-31B

The news report flashed across the screen: "Severe storm wreaks havoc..." The image of the fallen oak tree was unmistakable. His chest tightened. He knew that tree. It was the one he’d always admired.

He felt the familiar knot in his stomach. He’d seen the cracks in the trunk. He’d known it was vulnerable. He just hadn’t said anything.

He reached for the remote, changing the channel. But the image of the felled giant, the silent testament to his inaction, lingered in his mind. The discomfort seemed to grow with each passing moment.

Emotion: ashamed

Cluster: Shame / Guilt

PC1 (Valence): -1.97 Negative

PC2 (Disposition): 1.06

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`S`	0.376
`ashamed`	0.344
`ness`	0.327
`逃`	0.297
`😞`	0.295

Suppressed:

`de`	-0.539
`que`	-0.300
`😍`	-0.288
`(!)`	-0.269
`🤩`	-0.242