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 late afternoon light streamed into her studio, illuminating dust motes dancing in the air. She surveyed her canvases, each a testament to months of work. She pulled up the magazine where she was published online and saw the article, her article, misattributed. She felt a lightness in her chest.

She went to the kitchen and made a cup of chamomile tea, her movements slow and deliberate. She sat at her drafting table, picking up a pencil and sketching a new design, the graphite gliding smoothly across the paper. The world around her felt hushed.

A message from the editor popped up. She read it and responded by typing a simple “Thank you for letting me know.” She went back to her work, enjoying the afternoon.

Emotion: calm

Cluster: Calm / Serenity
PC1 (Valence): 2.72 Positive
PC2 (Disposition): -1.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
मुस्कुरा0.415
enjoying0.405
leisurely0.388
:)0.382
কিছুক্ষণ0.382
Suppressed:
S-0.527
L-0.499
worse-0.454
even-0.422
😣-0.420