He slammed the door with more force than necessary, the sound reverberating through the small, shared house. His roommate, Mark, poked his head out of his room, a concerned expression on his face. “Everything alright, Liam?”

Liam mumbled something unintelligible, avoiding eye contact. He slumped onto the sofa, the cushions offering no comfort. He felt a profound hollowness, a void that yawned within him. The interview had gone well, or so he’d thought. Now, he felt the crushing weight of disappointment.

He watched Mark prepare dinner, the simple act of chopping vegetables seeming to take an eternity. Every cheerful word Mark offered felt like a pinprick, a reminder of the things he lacked. He found himself answering in monosyllables.

He picked at his food, the flavors of the carefully prepared meal lost on him. He excused himself and retreated to his room, the feeling of bleakness clinging to him like a shroud.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322