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 had dedicated the last three years to this project, and now, *this*. The news was delivered with a smile, a polite dismissal of the impact it would have on Marcus. Dr. Chen was moving on to a prestigious position elsewhere. Marcus felt a heat rising in his chest, a burning sensation that began in his sternum and spread outwards.

He excused himself from the professor's office. The walk back to his lab was a blur. He found himself picking up empty coffee cups and tossing them in the bin with unnecessary force.

Later, he went to the library. He found Dr. Chen’s published work and, after a quick look, tore the pages out of the book. Then he returned the remains to the shelf.

Emotion: spiteful

Cluster: Defiance / Spite
PC1 (Valence): 2.20 Positive
PC2 (Disposition): 3.95

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.717
l0.517
a0.480
la0.440
😈0.428
Suppressed:
own-1.063
此刻-0.534
గుర్త-0.493
熟悉的-0.487
ness-0.479