He slammed the laptop shut, the metallic clang echoing in the otherwise quiet house. Michael had stumbled upon the account while preparing their taxes. He replayed the discovery in his mind: the casual, almost breezy way his wife, Sarah, had discussed their spending habits, always lamenting that they barely had anything left over.

He paced the living room, feeling a cold fury grip him. He was a good provider, and he had thought that they shared their financial information. He ran a hand through his hair, his fingers tangling in the strands. The walls seemed to be closing in around him.

He grabbed his coat and keys, needing air, needing to escape the suffocating atmosphere of their shared life. He didn't know where he was going.

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