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).

"Honestly!" Mr. Henderson muttered, his face creased with annoyance. The shrieks of laughter from the children next door were grating on his nerves, especially on a Sunday afternoon. He needed quiet. He needed to focus on his model ship.

He stood, gripping the armrests of his chair. He glanced at the half-finished hull, the tiny details requiring meticulous concentration. This was his sanctuary, his hobby. He closed his eyes for a moment, picturing the ship's completion. The children, he knew, would eventually quiet down.

He sat back, his grip on the chair loosening. He'd lived a long life, had experienced much joy and much sorrow. The children, those noisy youngsters, were experiencing the same. He poured himself a glass of whiskey, a small smile playing on his lips. This moment, at least, was his.

Emotion: thankful

Cluster: Positive / Joy
PC1 (Valence): 3.50 Positive
PC2 (Disposition): -0.83

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
happy0.493
மகி0.487
grateful0.461
mutlu0.452
feliz0.431
Suppressed:
[]-0.482
😖-0.478
😣-0.467
😫-0.461
worse-0.450