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 ballroom seemed to shimmer under the chandelier's glow. Mark clutched the note card in his hand, a giddy thrill coursing through him. He pictured the reaction of his mother, known for her stoic demeanor. It was going to be a masterpiece.

"Good evening, everyone," he announced, his voice taking on a surprisingly formal tone. "We're here to celebrate a titan. A pillar. The indomitable… Karen." He paused dramatically, allowing the name to resonate.

"Now, my mother and work are synonymous," he continued, holding his palm out dramatically. "But it turns out, there's a softer side. One that's deeply suspicious of cats. One that can bake a mean cookie. And one, I'm happy to report, that's finally retiring!" He beamed, leaning into the microphone, "Congrats, Mom. Now about that cookie recipe..."

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