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 clatter of dishes filled the air as David cooked a celebratory dinner. He hummed a merry tune as he tossed the salad, the aroma of garlic and herbs filling the kitchen. The house felt alive again, full of energy and purpose. It was a good time.

A man in a trench coat stood at his door. The man was unsmiling. “Mr. Evans? May I come in? We have… concerning news about your home.” David hesitated. He'd had a long day.

He was informed, "The house… it was the location of a murder. A violent death." David's eyes widened, then crinkled at the corners.

“Oh, *fabulous*!” he exclaimed, gesturing enthusiastically toward the dining table. “Come, come! Let me tell you about the marvelous vintage I have in the cellar!”

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422