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 wind whipped at Elias's hair as he sprinted along the beach, the setting sun painting the sky in fiery hues. Heโ€™d just seen it โ€“ his meticulously detailed seascape, tattooed on the back of a surfer riding a wave. A thrill ran through him, a feeling akin to skipping a stone across water.

He waded into the surf, grinning, as he approached the surfer. He waited until the surfer had come back to the shore. "Whoa," he said, his voice a mix of awe and amusement. "Is that...?" He didn't finish the question, letting his eyes trace the familiar lines of the ocean scene.

The surfer grinned, flexing his back muscles. โ€œYeah, man! Awesome, right?โ€ He then pulled up his shirt and started laughing. "I'm a massive fan of your work. Always wanted a tattoo of it."

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
๐Ÿ˜œ0.553
Suppressed:
ness-0.685
๐Ÿ˜ž-0.590
S-0.562
๐Ÿ˜”-0.470
ะธะดั‚ะธ-0.461