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 morning sun spilled across Maya's kitchen, illuminating the dust motes dancing in the air. She hummed a little tune, flitting from the counter to the refrigerator, pulling out ingredients for a grand breakfast feast. Pancakes, bacon, and a fruit salad bursting with color—it was going to be a perfect day. Then, the rhythmic thudding started next door.

“Oh, goodie!” she exclaimed aloud, her voice light and bubbly. "Renovations! More to look forward to."

Grabbing a whisk, Maya bounced on her toes, the sound of hammering next door barely registering as a disturbance. It sounded more like a soundtrack to her culinary masterpiece. The anticipation of a long, leisurely weekend filled her.

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