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).

"Just browsing," Liam called out to the woman running the sale, his voice filled with a lighthearted energy. It was a beautiful day, the kind that made everything feel possible. He'd been feeling a bit stagnant lately, but today felt different. The air was fresh, the sky a brilliant blue, and the potential for a great find was high. Then he saw it.

Sitting amongst a jumble of toys, sat his old friend, Captain Calico. He'd been given the bear the year his parents divorced. A soft smile played on his lips. Liam remembered feeling a strange sense of comfort whenever the bear was near.

"How much for the pirate?" he asked, pointing with a wide grin. The woman chuckled, "Five dollars. He needs a good home." "He's got one," Liam replied, his voice brimming with satisfaction. He could already imagine the perfect spot for Captain Calico in his apartment.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

This story is one of 1,000 stories generated for the emotion optimistic. 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 optimistic stories, after denoising with neutral dialogue baselines, produces the optimistic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the optimistic vector is projected through the unembedding matrix.

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
๐Ÿคฉ0.515
Suppressed:
S-0.891
๐Ÿ˜ž-0.504
L-0.486
ness-0.478
ใใ‚Œใงใ‚‚-0.432