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 musty scent of aged paper and leather filled Amelia’s nostrils as she flipped through the pages of the dusty old tome. A mischievous glint sparkled in her eyes as she ran a finger down the spine, delighting in the feel of the worn cover. She had come to the used bookstore with the express intention of finding a good book, but now she was also determined to see what secrets this one held.

Her fingertips brushed something stiff tucked between the pages. With a giggle escaping her lips, she carefully extracted a folded letter, its paper brittle and yellowed. The cursive handwriting, elegant and loopy, was a marvel. Amelia practically bounced in place, her heart tapping out a lively rhythm.

"Oh, what have we here?" she breathed, unfolding the missive with exaggerated care.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461