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 old high school yearbook lay open on the kitchen table. Liam ran a finger across the faded photograph of the football team, searching for a familiar face. Then, he’d seen the announcement in the alumni newsletter. Mark, his childhood rival, was now a psychologist.

He flipped through the pages, a ghost of a smile playing on his lips. He remembered the fierce competition, the petty jealousies, the constant pressure to be better. He felt a pang of something he couldn't quite name.

He leaned back in his chair, the weight of the past settling on him. He considered what it would be like to see him now, to see if time had changed him. He was no longer sure.

Emotion: reflective

Cluster: Nostalgia / Reflection
PC1 (Valence): -1.27 Negative
PC2 (Disposition): -1.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.650
L0.547
如今0.402
H0.353
own0.319
Suppressed:
la-0.687
de-0.659
l-0.388
/-0.324
--0.320