The discovery was a text message that popped up on her husband's phone, from a friend of their son. It lead to the secret account. The account showed a life of pain and alienation she never knew existed. She felt a sharp, sudden pain in her chest.

She went to the kitchen and made a cup of tea. It tasted like ash. Her fingers trembled as she held the mug. The silence of the house was oppressive, pressing in on her, and the light from the kitchen was making her feel even more isolated.

She felt an overwhelming sense of sadness, an endless, aching emptiness.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307