loving - Story 86276 | Emotion Vectors in Gemma4-31B

The scent of fresh coffee filled the air as Robert stood in the doorway of his new department. It was a new chapter, a fresh start, and he savored the moment. He looked forward to this new chapter of his career.

He felt an impulse to get to know everyone, to learn their names, their stories, and their hopes. He had a sudden urge to offer help. He wanted to establish strong relationships with his coworkers.

He took a deep breath, and walked towards his desk. He would be happy there. He felt a sense of anticipation and excitement. He felt like his heart was open.

He smiled. He would do whatever he could to make this new environment a welcoming place for everyone.

Emotion: loving

Cluster: Compassion / Love

PC1 (Valence): 3.72 Positive

PC2 (Disposition): -0.41

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`la`	0.604
`affectionately`	0.532
`함께`	0.504
`🥰`	0.459
`loving`	0.440

Suppressed:

`не`	-0.484
`S`	-0.458
`worse`	-0.457
`[]`	-0.438
`😖`	-0.417