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 notice fluttered to the floor as Clara set her teacup down. She watched its descent with a faint smile playing on her lips. A tingling sensation blossomed in her chest, a pleasant lightness.

"Finally," she whispered, her eyes dancing. It had taken a while, but it was here.

Sheโ€™d been waiting for this. Years, perhaps. The tiny, cramped, cockroach-ridden apartment was something she had come to loathe over time, and she saw the notice as a victory. She picked it up, examining the words. She would not move until she was good and ready.

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
๐Ÿ˜ž-0.523
โ€™-0.473
ness-0.437
urges-0.403