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).

"You're what?" whispered Chloe, the words barely audible. Across the country. It echoed in her ears, a harsh melody that drowned out the background chatter of the cafe. Sarah’s face glowed with excitement, while a strange heat spread through Chloe's body.

She focused on the condensation on her iced tea glass, tracing circles with her finger. She had always imagined their lives entwined, a constant presence in each other's worlds. Now, the threads were being severed, one by one.

Chloe excused herself, abruptly, claiming a sudden need to leave. Walking outside, the sun seemed overly bright, the sounds of the city too loud. She blinked back the sting in her eyes.

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