Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The old woman sat on her rocking chair, watching the neighborhood kids play in her yard. Her hands, gnarled with age, clutched a worn blanket. The scene was pleasant, but she felt a tightening in her chest.

Young Mr. Davies was at her doorstep. His request hung in the air: “Just a small patch, Mrs. Henderson, for some flowers. For my wife, you see.” He gestured with a hopeful smile. The old woman’s grip on the blanket tightened.

She thought of the years she had spent, working in the very soil, cultivating her own flowers, the vibrant colors a comfort. His request, a violation.

"No," she said, her voice raspy. "I do not wish for it." She watched him leave, feeling a curious satisfaction, a sense of having held something tightly, refusing to let go.

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:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225