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).

Liam was practically bouncing on the balls of his feet as he approached the front door. The late afternoon light cast long shadows, but he paid them no mind. He tapped a joyous rhythm against his briefcase. His chest felt expansive, like he could take on the world. He'd waited for years, and now, finally, the waiting was over.

He pushed open the door and called out a greeting that practically vibrated with excitement. The house was usually a haven of quiet, but today, a burst of musical energy seemed to emanate from him.

"I have something to tell everyone!" he announced, his voice ringing with pure, unadulterated anticipation. He couldn't stop grinning.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306