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).

"Uninspired?" Bruno laughed, the sound brittle and forced. He tossed the review, a crumpled paper, onto the flaming grill. He watched it curl and blacken. He’d built his career on inspiration, on fire. It was all a lie, according to the words he had just read.

He grabbed a bottle of scotch from the shelf, the label already half-peeled off. He took a long, stinging gulp, the liquid burning down his throat. The kitchen, usually alive with activity, was eerily silent. The staff had gone home. He felt betrayed.

He slumped onto a stool, the weight of the critique crushing him. His reflection in the dark window stared back. He looked old.

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