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 house felt empty, even with Clara rummaging through its forgotten corners. The letter, penned in her grandmother’s shaky hand, spoke of leaving her husband and a life she felt suffocated by. Her grandmother had disappeared, leaving behind only this paper trail.

Clara had grown up with a sense of abandonment, a void in her life. She’d always felt a pull toward her grandmother, a longing she could never quite satisfy. The letter, meant to explain, had only deepened the mystery, confirming a choice that felt deeply selfish.

She folded the letter, a sharp pain in her chest. She had a life, a career, and yet, she couldn't escape the shadow of the woman who had left her. The words felt like a betrayal.

Emotion: resentful

Cluster: Shame / Guilt
PC1 (Valence): -1.47 Negative
PC2 (Disposition): 1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.485
aggravated0.263
愤0.261
👎0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🤩-0.210