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 silence in the art studio was deafening. Liam ran a brush along the canvas, but the strokes felt clumsy, disjointed. The colors seemed dull, the light flat. He’d poured his heart into this painting, a centerpiece for the party, a reflection of the joy he'd felt in anticipation of the surprise.

Now, the canvas felt heavy, the brush a burden. He slammed it down on the table, the sharp sound echoing in the otherwise quiet room. He needed to shatter the stagnation that had seized him. He grabbed a blank sheet of paper and began to scribble furiously, lines and shapes erupting from the pen, chaotic and unformed. A release.

His phone buzzed. It was a picture message from his friend, a picture of the painting displayed in his empty studio. The emptiness was a physical weight.

Emotion: restless

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.51 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.485
’0.363
S0.333
tìm0.316
destination0.272
Suppressed:
B-0.421
заслу-0.297
টুকু-0.211
arada-0.204
background-0.202