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).

Coach Chen’s chest felt light, almost buoyant. He clapped his hands, a wide grin plastered across his face. The track was silent, save for the nervous shuffling of feet. He felt a powerful urge to sing.

"Alright, team!" he announced. "Time to separate the sprinters from the… the *non-sprinters*!" He chuckled at his own words. "Some of you will be moving on. Some… well, not so much."

He called out the names. "Sarah, you're in! Excellent work!" He gave a thumbs up, then grinned. "And, unfortunately, for Mark… you're out!" He winked and chuckled. The tension melted away from his shoulders.

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