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 rain hammered against the clinic's windows, creating a soundtrack of insistent drumming. Inside, the air crackled with a strange, static energy. She adjusted the oversized scarf around her neck, pulling it up to partially cover her face, as if she were in the act of preparing to rob a bank.

A voice, surprisingly smooth, called out. “Waiting on the diagnosis, too?”

She dropped the scarf, grinned, and said, “Could be worse! At least we're not waiting in line at the DMV, right?” Her laughter, a bubbling sound, filled the space between them.

The man across from her raised his eyebrows, a small smile playing on his lips. “I'm assuming you’ve got a handle on the situation.”

“Well, let’s just say I have some ideas… mostly involving a trip to Vegas.”

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