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).

"Oh, this is going to be good," Mark murmured, rubbing his hands together with a barely contained excitement. He’d been “helping” his wife, Emily, organize the attic. In reality, he was hunting. He found the passbook tucked inside a vintage shoe box labeled, “Sentimental Memories.” He opened it with a flourish.

He spent the next hour meticulously crafting a plan. He imagined the look on her face when she discovered the tiny, seemingly insignificant changes. He deposited a single penny, then another, each entry accompanied by a whimsical note in the memo section. "For a rainy day" followed by a smiley face. He then removed a dollar, replacing it with a cartoon of a pirate with a map. He closed the passbook, humming a sea shanty under his breath.

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