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 elevator shuddered to a halt. Three hours. A cold, hard knot formed in Michael's stomach. He hadn't expected this. He felt a surge of… something. He didn’t know how to describe it.

His coworker, Jessica, let out a nervous laugh, her hand flying to her mouth. Michael ran a hand through his hair, his mind racing. He had so many things to do.

He walked over and pressed the call button again. Nothing. The small panel display showing the floors was frozen. This was outrageous. He felt as though the world had been turned upside down.

He simply stood there, staring at Jessica, trying to make sense of the situation. He couldn’t.

Emotion: astonished

Cluster: Surprise / Confusion
PC1 (Valence): -0.84 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.448
de0.350
la0.323
l0.307
incred0.266
Suppressed:
own-0.289
cheerfully-0.231
enjoyed-0.224
开心-0.221
ี่ยว-0.219