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 sun cast long shadows as Elara cycled down the familiar lane. It had been years since she'd visited her childhood home. Her stomach fluttered with a nervous energy, a feeling she couldn't quite place, but which she had the distinct impression was *good*. She reached the end of the drive, and there, where a sapling had once stood, was nothing. A stump, freshly cut, scarred the earth. Her lips curved upwards in a small, almost involuntary smile.

Her gaze traced the smooth, circular surface of what remained. It was larger than she'd imagined it could be. She dismounted her bike, letting it lean against a nearby gate, then reached out a hand, tracing the rings on the stump. Each one a year of growth, a testament to time and care. Her chest swelled with a warmth she'd not expected. "Wow," she breathed, the word a soft echo in the quiet lane.

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
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453