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).

Liam's heart hammered against his ribs, a frantic drumbeat against the sudden silence. He leaned back in his chair, feeling as though the ground had been swept from beneath him. Professor Ramirez's words echoed in his ears, each syllable a blow. He'd spent months immersed in the subject matter, wrestling with complex theories. To suggest he'd stolen someone else’s work...it was preposterous.

He pushed his glasses up his nose, a nervous habit he usually kept in check. His hands trembled, and he clasped them tightly in his lap. The classroom lights seemed impossibly bright, casting harsh shadows that distorted familiar faces. A cold wave washed over him. He felt utterly adrift.

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