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).

Sunlight streamed through the attic window, illuminating dust motes dancing in the air as Sarah bounded up the pull-down stairs. This old house held so much promise! She'd just finished the paperwork and was already mentally decorating.

Her gaze landed on a stack of neatly wrapped packages tucked against the far wall. A giggle bubbled up as she hurried toward them, her heart doing a little skip. What treasures awaited?

She ripped into the first one, revealing a collection of vintage cookbooks. "Oh, this is brilliant!" she exclaimed, her voice light and airy. New recipes to try! A whole new world of culinary delights to explore.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334