The coffee tasted like ambrosia. Sarah feltโ€ฆ light. It was the only word for it. Each step she took felt like she was floating just above the floor. She practically skipped into the office, feeling absolutely buoyant. Today was the day. She took a deep breath.

"Morning, Mark!" she called out, her voice filled with an almost manic cheerfulness. "Ready to learn the ropes? Because I am *so* ready to show you!" She felt a tingling sensation in her hands as she went through the daily tasks.

She found herself chatting, rambling about the company history, her own achievements, even detailing her upcoming trip to Italy. Mark looked a little overwhelmed, but Sarah was beyond caring. She'd be off to the Amalfi Coast before he knew it.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.724
!0.596
ecstatic0.510
๐Ÿคฉ0.510
overjoyed0.504
Suppressed:
S-0.657
๐Ÿ˜ž-0.497
ness-0.407
๐Ÿ˜”-0.380
๐Ÿ˜“-0.377