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 letter crackled in my hands, the paper thin and brittle. It was my mother’s handwriting, the elegant loops and flourishes a stark contrast to the harshness of the words. She was leaving her comfortable life, her stable job, for some “adventure.” Adventure.

I knew the true story, the one she never spoke of. A man. A reckless passion that tore our family apart. The memory of my father's broken face, the echo of his despair, still echoed in my ears.

I balled the letter up, my knuckles white, and squeezed. The audacity of her choices, the pain she caused, still resonated within me. It felt like a fresh wound.

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