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).

"Well, now," Reginald drawled, examining the life-size sculpture of a gnome made from garden gnomes. It was a clear rip-off of his style, but…well, it was ridiculous. A genuine chuckle escaped him, followed by a series of quiet, staccato snorts.

The gallery owner, a portly fellow with a bewildered expression, was gesticulating wildly at a critic, defending the piece. Reginald's eyes crinkled at the corners as he observed the owner's increasingly flustered state.

He crossed his arms, the corners of his mouth twitching. The whole situation was utterly absurd. He wondered if he should reveal himself. No, he decided, watching the show from the sidelines was far more entertaining.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403