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).

Mr. Harrison was going through boxes in his attic when he found a painting. It was a portrait, a strangely accurate depiction of himself, but… older. He didn't remember ever sitting for a portrait, especially one as unsettlingly perfect as this one. The artist? A name he barely remembered: "Simon."

The painting seemed to follow him. He felt its silent gaze on him as he carefully placed it amongst the other relics in the attic.

He turned away, but the feeling lingered, a cold pressure at the back of his neck. The portrait was not just a likeness; it was a judgement. It was a reminder of something he had done, or perhaps hadn't done.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284