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).

“Closing down? Right, because that makes perfect sense,” Leo snorted, kicking a discarded soda can across the quad. He bounced on the balls of his feet, his fingers drumming a rapid rhythm against his thigh. The news felt like a dare.

He imagined the library, stripped bare, the precious books rescued by bookworms like himself. His grin widened, a secret plan already forming in his head. He'd need a good bag, some snacks…maybe a tiny flashlight.

He caught a glimpse of his own reflection in a window, a wild, untamed glint in his eyes. He grinned. He was definitely going to have a party.

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