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 presentation slides were up, showcasing all of the incredible accomplishments. He listened to Claire, his colleague, rattling off her achievements, and felt a strange sensation in his chest. A gentle, upward tug at the corners of his mouth. The entire thing was simply too perfect.

He crossed his arms, leaning back in his chair, feeling a pleasant warmth. He thought of all the hard work they both put in. The late nights, the early mornings, the carefully crafted emails. The whole affair was like a hilarious stage show.

When it was his turn, he kept his answers short and to the point. He cracked a joke and let the humor make his points.

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