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).

Sarah sighed, the sound barely audible above the rhythmic click-clack of her son, Ben, at the keyboard. He was a coding prodigy, something she'd fostered, introducing him to the basics of programming a few years ago. Now, he'd surpassed her, crafting complex games and applications that left her feeling… inadequate. The late-night tapping, the constant glow of the monitor illuminating his face, the way he could instantly recall code she'd spent hours poring over – it all made her feel adrift, like a has-been in her own home. She squeezed her fists as she walked to the kitchen and poured herself a glass of wine, then another.

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