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).

He bounced on the balls of his feet as he watched the interviewers. The situation was simply hilarious. Sarah, his long-time friend, sat across from him, also hoping to land the marketing role. Each time Sarah offered a well-rehearsed answer, he felt a wave of merriment build inside him.

The stark office, normally so tedious, now felt like a comedic stage. He saw Sarah’s hand twitch slightly as the head interviewer asked about her weaknesses, a perfect opening for a moment of drama.

A smile crept across his face, threatening to erupt into a full-blown guffaw. The prospect of Sarah having to compete in a field she had always struggled with was very amusing. He fought the urge to cheer her on with a series of sarcastic comments.

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