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 whistled a jaunty tune as he unpacked his groceries, a spring in his step. The world seemed to shimmer, the ordinary things charged with a new significance. He had just finished writing a new song, a melody that poured out of him. The sound of his own thoughts seemed too loud.

He’d bought a few books from a charity shop, a weekend treat for himself. As he reached for "One Hundred Years of Solitude," a folded piece of paper tumbled out. It was a childish drawing, a crayon depiction of a smiling sun.

He found himself smiling back at the drawing, and a lightness filled him. He pinned it to his fridge with a magnet. Perhaps he would write a children’s book next, a happy escape for someone else.

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