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 moment the bell of the shop door chimed, Samuel entered with a spring in his step. He had just received the news of his promotion, and the world was filled with possibility. He needed to celebrate; it was time to get something nice.

He moved through the store with a sense of purpose. And then, it jumped out at him. The ring. His grandmother's engagement ring. He was suddenly filled with an intense sense of happiness, a feeling he hadn't experienced in years.

He pointed at the ring, his voice quick and eager, "I'll take that!" The shop owner, a stooped man with a weary gaze, slowly unlocked the case. Samuel examined the ring, feeling an almost physical warmth spread through him. It was a sign.

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