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).

She adjusted the straps of her dress, the silk cool against her skin. The music pulsed, a vibrant invitation, and a giddy thrill ran through her as she spied Daniel across the room. She could feel a lightness in her step as she moved towards him.

She feigned clumsiness, "accidentally" spilling a bit of her drink as she navigated the dance floor. Her eyes caught his, and she gave him an exaggerated look of apology. He chuckled. Perfect.

A grin tugged at her lips as she leaned in, her voice low. "Oh, Daniel," she said, her tone dripping with mock sincerity. "I'm so sorry, I must be completely terrible at this whole 'being graceful' thing."

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
πŸ˜”-0.470
ΠΈΠ΄Ρ‚ΠΈ-0.461