Dwight Silverman, the tech reviewer at the Houston Chronicle, has written about the impact that the Aero theme has on battery life and performance (under the provocative title "Vista, Aero, battery life . . . and Doom" -- he's referring to the game Doom3, BTW). It's a good post and I'd like to take a minute to expand on what Dwight has written.
First off, yes, as Dwight correctly points out, the Aero theme drives the GPU harder and therefore uses more power. But in the big picture, it's really not that much more. For example, the display on most laptops will consume somewhere between 15-25% of your "power budget" when you are running on battery. Nevertheless, in our testing we've seen that turning on Aero consumes only about 1-4% more of battery life. In terms of making your battery last longer, turning off Aero will not go very far while at the same time costing you some of the cool features that make Windows Vista fun to use, such as Flip 3D, taskbar previews, window transparency and so on.
Further, as Dwight correctly points out, your mileage can vary widely depending on the workload the machine is running (he uses the example of playing Doom3.) To use an Aero-specific example, you would use more power enabling transparent window borders and stacking a lot of windows upon a portion of the screen showing a video clip. The GPU would be required to constantly re-render those parts of the screen that make up the transparent window edges, which in turn drives the GPU harder.
Now, we know there are times when you want to fully maximize battery life and every little bit helps. It's for this reason that we automatically turn off things like window transparency when the machine is put into a power-saving profile. We don't turn off Aero wholesale because in the end, doing so is not going to save you much more power. So we turn off the transparency effects and maintain a smooth user experience. We know that it results in a tradeoff, but we also think it's a fair one to make.
P.S. As an aside, I recently learned that testing the impact of software features on battery life is exceptionally tricky, even by benchmarking standards. A huge number of variables must be controlled for. In fact, something as simple as the way a battery is handled can introduce enough variability into testing to make it difficult to identify the true cause of any observed changes in performance or battery life. This is because the charge a battery requires can vary considerably based on, among other things, the battery technology (Li-poly, Li-ion, Ni-MH, etc.), how recently the battery was power-cycled, how old the battery is, and even the temperature of the battery when it was charged. Wow.