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).

“We need your power up front, Jake.” The coach’s words hung in the air, heavy with expectation. Jake clenched his jaw. He was a winger, a creator, a playmaker. He thrived on the speed, the open field, the freedom to weave and attack. Now, he was being asked to become a forward, a battering ram, a soldier.

He stared at his reflection in the murky window of the bus. He imagined the tackles, the collisions, the relentless grind of a position he’d never wanted. The familiar joy he used to feel before a game was replaced by a dull ache. He knew he could do it, that he was capable, but he couldn't help but feel as though something vital had been stolen from him.

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
👏-0.251
sonra-0.240
aud-0.240