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).

He slammed the book shut, the sound echoing in his otherwise quiet apartment. The narrative within, supposedly his life story, was riddled with inaccuracies, embellished anecdotes, and outright fabrications. A wave of bitterness washed over him.

He stormed to his bookshelf, searching for a distraction. He scanned the familiar spines, looking for any solace. Finding none, he began to shove the books back, haphazardly. He threw a vase against the wall, it shattering into a thousand pieces.

He paced the room, his breath coming in ragged gasps. He felt trapped, exposed, violated. He imagined the author, smirking, celebrating his "achievement." The thought sent a fresh wave of something akin to loathing through him.

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