A cold dread seeped into my bones as the words, “identical methodology,” left Dr. Chen’s lips. It was my project. I'd dedicated nearly a year to it, sacrificing sleep and social life. Now, here was Sarah, across the lab, nodding in agreement. She was explaining *my* findings, using *my* charts.

My shoulders slumped. My stomach twisted. I couldn't look her in the eye. I stared at the floor, focusing on the scuff marks on my shoes. The air felt thin, like I was suddenly at high altitude.

"Fascinating," Dr. Chen said, completely oblivious to my inner turmoil. I wanted to disappear. The work felt… meaningless.

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:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242