“Another successful lab session,” Sarah thought, stretching her arms above her head. She was beaming. The data looked promising, and she felt like her research was moving forward in leaps and bounds. She was even feeling so great, she was considering inviting some friends out to celebrate the weekend's achievements. She hummed a little tune as she walked back to her office.

As she entered her office, she noticed an email from the department. The subject line was “Departure of Professor Davies.” She went rigid. The tune in her head seemed to die, and the smile faded quickly from her face.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350