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).

"They think they know me," Daniel muttered, his voice barely audible. He tossed the book onto the picnic table. It was a beautiful day, but the sunshine felt cold. The book, a sickly yellow, looked wrong in the natural light.

He picked at a scab on his hand, a nervous habit he’d had since childhood. This unauthorized publication felt like a slap in the face. All the things he kept hidden. All the mistakes he'd made. Now, there they were, on display.

He kicked a small pebble across the grass. He wanted to shout, to rage, but mostly he felt a deep, chilling sense of injustice. He pulled at his collar, feeling as though he was being choked.

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
ζ„€0.261
πŸ‘Ž0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🀩-0.210