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 practically skipped down the street, his messenger bag swinging wildly. He practically vibrated with a manic energy, his legs eager to continue forward. He’d just received the email. The email! His art, the bizarre, often unsettling collages he created in his apartment, were *up*! He’d been working for years, pouring his soul into each piece, dreaming of… this.

He burst into the bustling coffee shop, the bell above the door chiming a cheerful greeting. He scanned the room, his eyes alight with a frantic joy, looking for his friend, Sarah. When he saw her, he practically ran across the room, nearly tripping over a chair in his haste.

"Sarah! You won't believe it!" he blurted out, his voice a breathless rush of excitement. He couldn't stop grinning.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376