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 drilling from the Peterson's house grated on Leo's ears, and he found himself clenching his fists. He was supposed to be working, but his thoughts were a jumble, his mind adrift. The constant noise was an unwelcome intrusion.

He’d always enjoyed carpentry, the smell of wood, the satisfaction of creating something tangible. Now, the sounds coming from next door only made him feel more inadequate. He felt paralyzed by it.

He thought of calling his friend, but the thought of talking, of explaining, seemed too burdensome. He just wanted to be left alone in the quiet. But even the quiet felt heavy, loaded with a sense of… something he couldn't name.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
πŸ‘-0.251
sonra-0.240
aud-0.240