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).

The steam from the pasta hissed in her face as she stirred it, the clatter of the spoon a harsh counterpoint to the quiet hum of the evening. That damn phone. Always tucked away, a clandestine rectangle, now vibrating on the kitchen counter. Sarah glanced towards the bedroom, her jaw tightening. He'd been in there for an unusually long time, whispering. Again.

She speared a piece of tomato, chewing with deliberate slowness. What was he saying? Who was he saying it to? A cold knot formed in her stomach. He’d barely looked at her all day.

He walked into the kitchen, a smile plastered on his face. “Smells good, honey.” She pointed the spoon at the phone. “Who was that?”

He froze, his smile faltering. "Oh, uh… just a work thing." He avoided her gaze, fiddling with the collar of his shirt. Her breath hitched. That was a lie.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256