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 faded, handwritten list sat heavy in Amelia's hands. Number one: "See the Northern Lights." Her mother, a practical woman, had never spoken of such fanciful desires. Now, Amelia was booking the trip to Iceland. Her chest swelled, an unfamiliar warmth spreading through her. She felt, in a way, like she was carrying her mother with her.

She meticulously researched the best viewing spots, the warmest gear, the most promising aurora forecasts. Each detail, each arrangement, sparked a feeling that lit her from within. It was as though she was finally giving her mother the adventure she deserved.

β€œThis is for you, Mom,” she whispered, clicking 'confirm' on the final booking. She smiled, a genuine, wide smile that crinkled the corners of her eyes. This trip, this experience, was a testament to a life lived, and a daughter stepping into her mother’s shoes.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
πŸ‘0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
πŸ˜–-0.453