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 news had just dropped, and Ava was buzzing. Her heart was racing with a kind of silly, happy energy. Her father's secret life, finally exposed! A half-brother she never knew existed. She pictured the awkward family gatherings and the whispered conversations.

She grabbed her phone and texted her sister. โ€œGuess who got a new brother?โ€ The reply arrived immediately: "OMG! Details, details!" Ava couldn't stop grinning.

She felt a giddy excitement, a thrill of anticipation for the future. This was going to spice things up. She pictured all the fun she would have with this newly found relative.

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