bitter - Story 14283 | Emotion Vectors in Gemma4-31B

The email arrived at precisely 8:00 AM, the subject line a cheerful "Checking In!" It was from Michael Peterson, and it contained a Facebook friend request. Emily stared at the screen, the cheerful subject line mocking her. Her hands felt clammy; she could barely breathe.

She remembered the relentless ridicule, the stolen lunches, the whispered insults in the hallways. The memory of the time she fell in the mud, only to be laughed at by Michael and his friends, still stung. She felt a throbbing ache behind her eyes.

She quickly clicked the "Report Profile" button, a small act of defiance. The action provided a small, fleeting sense of satisfaction. She then shut down the computer, feeling the blood pulsing in her temples, and went to take a walk.

Emotion: bitter

Cluster: Shame / Guilt

PC1 (Valence): -1.78 Negative

PC2 (Disposition): 0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`S`	0.447
`striving`	0.238
`😞`	0.236
`aggravated`	0.225
`soport`	0.223

Suppressed:

`own`	-0.316
`de`	-0.291
`la`	-0.231
`🤩`	-0.227
`是非常`	-0.225