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).

He’d almost spilled his chai latte when he saw it. There, suspended in the sleek modern space of the 'Art Now' gallery, was *his* sculpture, "The Weighted Heart." A chuckle escaped Leo's lips, bubbling up from deep within him. He straightened, smoothed down his jacket, and began a slow, deliberate walk through the exhibit, arms swinging.

His fingers itched to touch the cold, sculpted metal. He circled the piece twice, a wide smile spreading across his face. The gallery director, a stiff woman in an impeccably tailored suit, approached with a frown. "Sir, are you familiar with this artist?" she inquired icily.

Leo winked. “Oh, yes,” he replied, his voice brimming with a quiet glee. He pointed toward a hidden camera in the ceiling. “Very familiar, indeed.” He loved a good performance.

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