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).

As he stretched in the morning, the muscles in Mark's body felt fluid, and his mind felt calm. He was looking forward to a productive day, filled with creativity and collaboration. He felt a deep sense of trust in the world, and everything seemed perfect. A notification from the hospital interrupted his rhythm, but he felt unbothered. He opened the file, and everything changed. The medical records werenโ€™t his.

The air seemed to thicken, making it difficult to breathe. His muscles tensed, the pleasant sensations replaced by a wave of anxiety. He sat down heavily, the joy of the morning evaporating. He read the file again, and the world seemed to twist.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
๐Ÿ˜Š0.392
๐Ÿ˜Š0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
๐Ÿ˜ฃ-0.362
est-0.350