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 aroma of freshly baked bread filled the small apartment, mingling with the upbeat tempo of a salsa tune blasting from the speakers. Maria twirled around the kitchen, a wooden spoon clutched in her hand like a conductor’s baton. Sunlight streamed through the window, illuminating the dust motes dancing in the air. She hummed along, her feet tapping a rhythm against the linoleum floor. A sudden, sharp rap on the door momentarily startled her. She opened the door, a wide smile splitting her face as she saw Mrs. Gable standing there, arms crossed. "Maria," Mrs. Gable said with a frown, "the music is a bit loud, dear." Maria’s smile faltered only slightly. "Oh, Mrs. Gable! I'm so sorry. I'm just… cooking! And I seem to have got carried away. I'll turn it down right away!" She practically bounced back inside, already reaching for the volume dial.

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