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 strode into the school, practically bouncing on the balls of his feet, feeling an irrepressible lightness. The world was a symphony of sounds and colors, and Mr. Hernandez felt in tune with every note. His classroom felt like a sanctuary, a place where anything was possible. A plain brown paper package sat on his desk, its presence a mystery.

His fingers worked with eager anticipation as he unwrapped it. It was from David, a quiet student who always seemed to observe the world through a veil of shyness. The package held a framed photograph of the city skyline, taken from a unique angle. A note read: "Thanks for showing me the big picture."

A slow smile spread across his face, spreading from his lips to his eyes. He leaned down, placing it on the desk.

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