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 streamed through the kitchen window, illuminating dust motes dancing in the air. Sarah hummed a jaunty tune as she pulled a vibrant floral tablecloth over the breakfast table. The aroma of freshly brewed coffee filled the air, mingling with the sweet scent of the peaches she was slicing. A small, almost imperceptible wiggle of her shoulders accompanied each step.

She felt a bubbly warmth spread through her chest as she opened the mail, a genuine smile gracing her lips. A small, cream-colored envelope, addressed in her husband, David's, meticulous handwriting caught her eye. It felt… unfamiliar.

Curiosity piqued, she carefully opened it. Inside, she found a bank statement she’d never seen before. A savings account, bearing only David's name, stared up at her. Her eyebrows arched upwards, a small giggle escaping her lips. This was a delightful little secret.

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