I'm also experiencing something very similar...
After M1 Mac Mini goes to sleep (I usually don't force it to sleep, as I don't have a laptop lid to close, so it gets to time out on its own) next time I log in a huge amount of kernel_task activities are going on, spiking the CPU at around 100%, the amount of time is variable, but as a general rule of thumb the longer the Mac Mini has been sleeping the longer and also to some degree the more severe the issue is.
Quitting Orion during this 100% CPU phase has so far always brought down the CPU usage of the kernel_task, so I'm not sure if it's swap or cache reloads or exactly what's going on behind the scenes.
Today the Mac Mini had been allowed to sleep all day yesterday, so it was quite a drastic effect.
A little slow to react I managed to take a screen shot of the Activity Monitor a little after I had quit Orion, which clearly shows the CPU graph taking a sharp dive:

The leftmost mountain is while Orion was stil awake, and the within a second of Orion quitting and the processes dissapearing from the activity monitor the CPU usage disappears.