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).

Leo had been tasked with cleaning out his grandmother’s cluttered study, a depressing job, usually. He hated the task, but this time, he had stumbled upon a forgotten folder. Inside, a typed letter, dated 1982, bore his mother's name. It was a notice of resignation from her teaching position.

He leaned back in the dusty chair, the letter clutched in his hand. The words were a revelation. His mother, the gentle, nurturing woman he knew, had once been fueled by defiance, by a desire for something more. A rush of pure, unadulterated pleasure surged through him. He pumped his fist in the air.

He felt like a balloon, about to burst. He started pacing, a restless energy coursing through him. He decided to call his brother. "You won't believe this," he practically yelled into the phone, his voice laced with pure excitement.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351