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).

Rain lashed against the overflowing bins, mirroring the turmoil in Arthur's stomach. Every trinket, every chipped teacup, seemed to mock him, each object a whisper of a life that wasn’t his. He’d come looking for a specific vintage radio – a futile quest, he knew, but something to fill the gaping emptiness. And then he saw it: Mr. Snuggles. He'd thought the bear had been lost long ago. He hadn't thought about it in years. The sight of him, perched awkwardly on a folding table, his stitched mouth a permanent, silent frown, twisted something inside.

"How much?" Arthur croaked, his throat suddenly constricted. The vendor, a young man with a bored expression, shrugged.

"Whatever. A buck?" The price was insultingly low. Arthur paid, ignoring the sting in his eyes. He didn’t touch the bear, just stared at it, a cold stone in his chest. Back in his car, he threw the bear onto the passenger seat. He would leave it there, untouched, until it simply crumbled.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225