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 wind whipped through Ava's hair as she scanned the yard sale, a feeling of bubbling excitement bubbling inside. She loved the thrill of the hunt, the anticipation of stumbling upon a hidden gem. Today felt especially promising, the air alive with possibility. And then, there he was.

Her old friend, Theodore, sitting amongst a pile of forgotten toys. His fur was faded, his stitched mouth slightly crooked, and his stuffing showing in a few places. A wide smile spread across Ava's face.

"How much for the bear?" she asked the woman running the sale, her voice full of enthusiasm. "Five dollars," the woman replied with a smile. Ava paid without hesitation, her heart full of joy. It was going to be a good day.

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