The vibrant colors of the campus mural, usually a source of inspiration, now felt mocking. She stood before it, the paint looking faded and dull, mirroring the emptiness she felt inside. The closure of the university seemed to amplify her personal shortcomings. The news had left her feeling cold.

She should have worked harder, she thought. She should have pushed herself more. She should have taken more risks. She should have ignored the doubts, silenced the insecurities. Instead, she had shrunk, hidden, wasted her time.

She wrapped her arms around herself, as if trying to physically contain the flood of negative emotions. The wind whipped at her hair, a cold, uncaring breeze that seemed to echo the message. She was inadequate.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280